Mask pattern determination method and device, medium and product

Abstract

The invention discloses a mask pattern determination method and device, a medium and a product, and is applied to the technical field of semiconductors. In the method, the etching deviation is determined by a first etching pattern and a first photoetching pattern, and the first etching pattern is obtained by fusing a first sub-image and a second sub-image. The first sub-image is generated by the physical effect simulation unit based on the first photoetching pattern, and the second sub-image is generated by the neural network unit based on the first photoetching pattern. Wherein the neural network unit can effectively improve the fitting capability of the etching model to the data, so that the accuracy of the etching model is improved, and the accurate first etching deviation is obtained. And meanwhile, the physical effect simulation unit for etching simulates the actual physical effect, so that the condition of over-fitting of the etching model can be prevented.

Description

Technical Field

[0001] This application belongs to the field of semiconductor technology, and particularly relates to a method, device, medium and product for determining a mask pattern. Background Art

[0002] The most core step in semiconductor chip manufacturing is to transfer the design pattern of the chip onto the wafer. Among the numerous process steps in chip manufacturing, the processes directly related to pattern transfer are mainly lithography and etching. However, both the lithography process and the etching process will introduce deviations, resulting in differences between the lithography pattern and the etching pattern and the mask pattern. Therefore, when designing the mask pattern, it is necessary to compensate for the lithography deviation and the etching deviation. Currently, the lithography deviation is mainly compensated by Optical Proximity Correction (OPC). For the etching deviation, currently, an etching deviation table is mainly established to store the etching deviations corresponding to different patterns, and then based on the corresponding pattern style, the corresponding etching deviation is matched in the etching deviation table. For example, the etching deviation is determined according to the line width (width) and pitch (space) of the sides of the current polygon; and then the etching deviation compensation is completed.

[0003] However, etching is different from lithography, and its physical and chemical processes are more complex. For patterns with different line widths and pitches, the etching deviation will change. For simple patterns, the current method based on the etching deviation table can be applied. However, in actual production, the line density of the pattern will also affect the etching deviation. For complex patterns, it is difficult to achieve good results with the current method of looking up the etching deviation in the etching deviation table, resulting in an inability to accurately determine the etching deviation, and thus the finally designed mask pattern cannot meet the actual requirements. Summary of the Invention

[0004] Embodiments of this application provide a method, device, medium and product for determining a mask pattern, which can accurately obtain the first etching deviation of different lithography patterns through an etching model, and then determine the actually required mask pattern.

[0005] On the one hand, embodiments of this application provide a method for determining a mask pattern, including:

[0006] Determine a first mask pattern based on a first target etching pattern;

[0007] Obtain a first lithography pattern after lithography of the first mask pattern;

[0008] Input the first lithography pattern into at least one physical effect simulation unit of an etching model to correspondingly obtain at least one first sub-image, and input the first lithography pattern into the neural network unit of the etching model to obtain a second sub-image; the neural network unit is trained based on lithography pattern samples and corresponding etching image labels;

[0009] Based on a fusion unit of the etching model, fuse the at least one first sub-image and the second sub-image to obtain a first etched pattern after etching the first lithography pattern;

[0010] Based on the first etched pattern and the first lithography pattern, determine a first etching deviation of the first lithography pattern;

[0011] Based on the first etching deviation and the first target etched pattern, determine a first target mask pattern.

[0012] On the other hand, the determining the first target mask pattern based on the first etching deviation and the first target etched pattern includes:

[0013] Based on the first etching deviation, compensate the first target etched pattern to obtain a first target lithography pattern;

[0014] Based on the first target lithography pattern, perform optical proximity effect correction to obtain a second mask pattern;

[0015] In the case where the first etching deviation does not meet a first preset condition, update the first mask pattern to the second mask pattern; and return to the step of obtaining the first lithography pattern after lithography of the first mask pattern until the first etching deviation meets the first preset condition;

[0016] In the case where the first etching deviation meets the first preset condition, determine the current second mask pattern as the first target mask pattern.

[0017] On the other hand, the determining the first mask pattern based on the first target etched pattern includes:

[0018] Based on the first target etched pattern and a first corresponding relationship, determine a corresponding second etching deviation; the first corresponding relationship is the corresponding relationship between an etched pattern and an etching deviation;

[0019] Based on the second etching deviation, compensate the first target etched pattern to obtain the corresponding first target lithography pattern;

[0020] Based on the first target lithography pattern, perform optical proximity effect correction to obtain the first mask pattern.

[0021] On the other hand, after the fusion unit based on the etching model fuses the at least one first sub-image and the second sub-image, the method further includes:

[0022] Obtain a first target etching pattern corresponding to the first mask pattern;

[0023] Construct a training sample according to the first target etching pattern and the first etching pattern;

[0024] Perform model training according to the training sample to obtain a lithography compensation and lithography etching model.

[0025] On the other hand, after performing model training according to the training sample to obtain a lithography compensation and lithography etching model, the method further includes:

[0026] Determine a second target lithography pattern based on a second target etching pattern;

[0027] Input the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etching pattern, and input the second target lithography pattern into a pre-trained lithography compensation and lithography model to obtain a second lithography pattern;

[0028] Determine a third etching deviation based on the second etching pattern and the second lithography pattern;

[0029] In the case where the third etching deviation does not meet the second preset condition, compensate the second target etching pattern based on the third etching deviation to obtain a corrected second target lithography pattern;

[0030] Update the second target lithography pattern to the corrected second target lithography pattern; and return to the step of inputting the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etching pattern, and inputting the second target lithography pattern into a pre-trained lithography compensation and lithography model to obtain a second lithography pattern, until the third etching deviation meets the second preset condition;

[0031] In the case where the third etching deviation meets the second preset condition, determine a second target mask pattern based on the current corrected second target lithography pattern.

[0032] On the other hand, the determining the second target lithography pattern based on the second target etching pattern includes:

[0033] Determine a corresponding fourth etching deviation based on the second target etching pattern and a first correspondence; the first correspondence is the correspondence between the etching pattern and the etching deviation;

[0034] Compensate the second target etching pattern based on the fourth etching deviation to obtain the corresponding second target lithography pattern.

[0035] On the other hand, before inputting the first lithography pattern into at least one physical effect simulation unit of the etching model to correspondingly obtain at least one first sub-image, and inputting the first lithography pattern into the neural network unit of the etching model to obtain a second sub-image, the method further includes:

[0036] Obtain the lithography pattern sample and the corresponding etching image label;

[0037] Input the lithography pattern sample into the at least one physical effect simulation unit to correspondingly obtain at least one third sub-image, and input the lithography pattern sample into the initial neural network unit to obtain a fourth sub-image;

[0038] Fuse the at least one third sub-image and the fourth sub-image based on the fusion unit to obtain a second etched image after etching the lithography pattern sample;

[0039] Obtain the dimension difference between the first graphic key dimension of the etching image label and the second graphic key dimension of the second etched image;

[0040] Train the initial neural network unit based on the dimension difference to obtain the neural network unit;

[0041] Determine the etching model according to the neural network unit, the physical effect simulation unit, and the fusion unit.

[0042] On yet another aspect, an embodiment of the present application provides a mask pattern determination device, including: a processor and a memory storing computer program instructions;

[0043] When the processor executes the computer program instructions, the mask pattern determination method described above is implemented.

[0044] On yet another aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the mask pattern determination method described above is implemented.

[0045] On yet another aspect, an embodiment of the present application provides a computer program product, and when the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is caused to execute the mask pattern determination method described above.

[0046] A method for determining a mask pattern provided by an embodiment of the present application. In this solution, the etching deviation used for etching deviation compensation is determined by a first etching pattern and a first lithography pattern, and the first etching pattern is obtained by fusing a first sub-image and a second sub-image. The first sub-image is generated by a physical effect simulation unit based on the first lithography pattern, and the second sub-image is generated by a neural network unit based on the first lithography pattern. Among them, the neural network unit can effectively improve the fitting ability of the etching model to data, improve the accuracy of the etching model, and obtain an accurate first etching deviation, thereby ensuring the actual required mask pattern finally determined. At the same time, the physical effect simulation unit of etching simulates the actual physical effect and can prevent the occurrence of overfitting of the etching model. Description of the Drawings

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0048] Figure 1 The flowchart of the mask pattern determination method provided by an embodiment of the present application is shown;

[0049] Figure 2 The schematic diagram of the model simulation process provided by an embodiment of the present application is shown;

[0050] Figure 3 The first flowchart of designing the first target mask pattern provided by an embodiment of the present application is shown;

[0051] Figure 4 The second flowchart of designing the first target mask pattern provided by an embodiment of the present application is shown;

[0052] Figure 5 The first flowchart of designing the second target mask pattern provided by an embodiment of the present application is shown;

[0053] Figure 6 The second flowchart of designing the second target mask pattern provided by an embodiment of the present application is shown;

[0054] Figure 7 The flowchart of the training process of the etching model provided by an embodiment of the present application is shown;

[0055] Figure 8 The schematic diagram of the structure of the mask pattern determination device provided by an embodiment of the present application is shown;

[0056] Figure 9 The schematic diagram of the hardware structure of the mask pattern determination device provided by an embodiment of the present application is shown. Detailed implementation manners

[0057] The features and exemplary embodiments of various aspects of the present application will be described in detail below. To make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than limiting the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by showing examples of the present application.

[0058] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0059] In the current mainstream integrated circuit manufacturing process, in the lithography technology, the photoresist undergoes chemical changes under the exposure of special wavelength light, and then the pattern designed on the mask is transferred into the photoresist topography on the silicon wafer through development. The etching process is based on selectively removing unnecessary materials with the help of the photoresist topography, so as to finally create the required micro-patterns on the silicon wafer.

[0060] With the continuous evolution of the chip technology node, the size of its design pattern is much smaller than the wavelength of lithography (193 nm), which leads to the optical proximity effect and thus lithography deviation. To compensate for this deviation, OPC is required.

[0061] In the manufacturing process of integrated circuits, an etching process is also required after lithography. Etching will cause etching deviation, that is, the line width of the photoresist before and after etching is inconsistent. For example, when the wafer contains both sparse and dense patterns to be etched at the same time, the etching rate in the dense area is lower than that in the sparse area, which is called the microloading effect. Another example is in the etching of high aspect ratio structures, such as deep holes or deep trenches. The etching rate of smaller-sized holes or trenches is less than that of larger-sized holes or trenches, which is called the aperture effect.

[0062] It can be seen that etching different regions corresponds to different etching rates. On the one hand, this will cause changes in the overall pattern size after etching. More importantly, for patterns of the same size after lithography, their sizes after etching will also become different. When designing the mask pattern, etching deviation must be considered. Otherwise, even if the size of the lithography pattern obtained after lithography exposure meets the expectation, it will still deviate from the target size after etching.

[0063] Regarding etching deviation, currently, an etching deviation table (Bias-Table) is mainly established to store the etching deviations corresponding to different patterns, and then based on the corresponding pattern style, the corresponding etching deviation is matched in the etching deviation table. The current Bias-Table mainly determines the corresponding etching deviation according to the line width and pitch of the upper side of the current polygon. For simple patterns, it can barely meet the requirements. However, when the pattern becomes complex, the accuracy of the traditional method will become low.

[0064] For two sides with exactly the same line width and pitch, if the pattern density around them is different, it will lead to different final etching deviations. And matching the etching deviation according to the existing Bias-Table method will inevitably result in errors. With the continuous evolution of semiconductor technology nodes, the accuracy requirements for pattern transfer (lithography and etching) are getting higher and higher; while the traditional method cannot meet the actual needs.

[0065] Due to the limited accuracy of the Bias-Table-based method, to solve this problem, this application comes up with establishing an etching model to simulate the etching process. After simulating the etching image, the etching deviation can be determined based on the patterns in the etching image. First, a physical effect simulation unit Term can be established to establish a partial model according to the actual physical effects generated during the etching process. Since the accuracy of etching simulation only through Term is insufficient, therefore, on this basis, to further improve the accuracy of the etching model, this application also adds a neural network unit to the etching model, that is, introducing artificial intelligence (AI) to assist in etching modeling through AI, so that the etching model has high accuracy, and then the accurate etching deviation can be determined.

[0066] Based on this, the embodiments of this application provide a mask pattern determination method, device, medium, and product. First, the mask pattern determination method provided by the embodiments of this application will be introduced below. Figure 1 The flowchart of the mask pattern determination method provided by an embodiment of this application is shown. As Figure 1 shown, the method may include the following steps: S101 to S106.

[0067] S101: Determine a first mask pattern based on a first target etching pattern.

[0068] This application is commonly used in the design scenario of mask patterns. Therefore, before obtaining the first lithographic pattern after lithography of the first mask pattern, the first target etching pattern can be obtained, and based on the first target etching pattern, the first mask pattern can be determined.

[0069] In the design scenario of mask patterns, the first target etching pattern is the actually desired wafer pattern. As an alternative implementation, operations such as etching deviation compensation and OPC can be performed on the first target etching pattern to obtain the first mask pattern. At this time, the etching deviation can be determined through traditional solutions. However, since the accuracy of the etching deviation determined by traditional solutions is low, in this implementation, after obtaining the first mask pattern, the first etching deviation is re-obtained based on this solution, and then the first target mask pattern can be re-determined based on the first etching deviation, and the first target mask pattern is used as the finally designed mask pattern.

[0070] S102: Obtain the first lithographic pattern after lithography of the first mask pattern.

[0071] The first mask pattern is the pattern on the mask plate, which can be the pattern in the design process or the pattern actually existing on the mask plate. After the mask plate containing the first mask pattern undergoes the lithography process or lithography process simulation, the first lithographic image is obtained, and the pattern in the first lithographic image is the first lithographic pattern.

[0072] This application is commonly used in the design scenario of mask patterns. In the design process of mask patterns, it is necessary to first obtain the desired wafer pattern (i.e., the pattern on the wafer after processes such as lithography and etching), and then perform etching deviation compensation and OPC on the wafer pattern to obtain the mask pattern; the above process is a common mask pattern design process. As some feasible implementation manners, the first mask pattern mentioned in this application can be the above-mentioned mask pattern.

[0073] S103: Input the first lithographic pattern into at least one physical effect simulation unit of the etching model to correspondingly obtain at least one first sub-image, and input the first lithographic pattern into the neural network unit of the etching model to obtain a second sub-image.

[0074] The etching model provided in the embodiments of this application is used to process images to simulate the etching process, and then obtain the etched etching image. The first lithographic pattern obtained above mainly characterizes the pattern style and cannot be directly input into the etching model. Therefore, in order to simulate the etching process, corresponding images need to be generated. In practical applications, the processor can directly generate the corresponding optical image based on the pattern style of the first mask pattern, and then perform etching simulation based on the optical image of the first lithographic pattern to generate the corresponding sub-image.

[0075] The etching model in this embodiment consists of a neural network unit and at least one physical effect simulation unit.

[0076] The physical effect simulation unit is used to simulate some physical effects in the actual etching process, such as the microloading effect and the aperture effect, etc. Inputting the mask pattern into different physical effect simulation units can obtain the first sub-image after corresponding processing. For example, the Gaussian convolution term can be used to simulate the diffusion process.

[0077] The neural network unit is trained based on the lithography pattern samples and the corresponding etching image labels. Adding the neural network unit to the etching model can greatly improve the data fitting ability of the etching model. It solves the problem that the existing modeling method cannot quickly obtain a good model calibration result according to the measurement result due to the complexity of the etching process, that is, it improves the speed and accuracy of model calibration.

[0078] In addition, the neural network unit may suffer from overfitting. In this implementation, by simulating the actual physical effects through the physical effect simulation unit, it plays a role in preventing the model from overfitting. Moreover, when training the neural network unit, the model can be trained based on a large amount of Scanning Electron Microscope (SEM) image data, which can further reduce the problem of overfitting of the application network model.

[0079] S104: Based on the fusion unit of the etching model, fuse at least one first sub-image and the second sub-image to obtain the first etched pattern after the first lithography pattern is etched.

[0080] After obtaining the first sub-image output by the physical effect simulation unit and the second sub-image output by the neural network unit, it is necessary to fuse each image, and then obtain the first etched image after the first lithography pattern is etched. The fusion idea of the etching model can be specifically referred to the following formula:

[0081]

[0082] Among them, OutputImage is the first etched image, InputImage is the optical image input to the etching model, Term i (InputImage) is the first sub-image, n is the number of the first sub-images, and Neurom_NET(InputImage) is the second sub-image.

[0083] Figure 2 Shows a schematic diagram of the model simulation process provided by an embodiment of the present application. As Figure 2As shown, first obtain the first lithography pattern 201, and then generate the optical image 202 of the first lithography pattern 201. Input the optical image 202 into each physical effect simulation unit to correspondingly obtain each first sub-image 203. Input the optical image 202 into the neural network unit to obtain the second sub-image 204. Finally, the fusion unit based on the etching model fuses each first sub-image 203 and the second sub-image 204 to obtain the first etched image 205 after etching the first lithography pattern.

[0084] For the first etched image obtained by fusing the first sub-image and the second sub-image, extract the first etched pattern in the first etched image. As an optional implementation manner, the first etched image can be binarized based on a preset threshold, and then the first etched pattern (i.e., the etching profile) can be obtained.

[0085] S105: Determine the first etching deviation of the first lithography pattern based on the first etched pattern and the first lithography pattern.

[0086] After the first etched pattern is extracted, the first etched pattern can be compared with the original first lithography pattern to find the differences between the two and determine the difference value, i.e., the etching deviation. In practical applications, the pattern is usually broken, and then when determining the first etching deviation, the first etching deviation corresponding to each edge will be determined.

[0087] S106: Determine the first target mask pattern based on the first etching deviation and the first target etched pattern.

[0088] In the specific implementation, there is no limitation on how to determine the first target mask pattern based on the first etching deviation and the first target etched pattern; the corresponding scheme can be selected according to the actual situation. As an optional implementation manner, the first target etched pattern can be compensated based on the first etching deviation to obtain the target lithography pattern; then the optical proximity effect correction is performed based on the target lithography pattern to obtain the first target mask pattern.

[0089] In addition, after the first etching deviation is obtained, the first etching deviation can also be compared with the etching deviation obtained based on the traditional scheme. When the gap between the two is small, it indicates that the etching deviation obtained based on the traditional scheme is accurate enough. At this time, the first mask pattern can be directly used as the first target mask pattern.

[0090] In addition, as mentioned above, the pattern is usually broken to obtain multiple edges, and each edge corresponds to a first etching deviation. Therefore, as an optional implementation manner, the above process can be sequentially executed for each edge separately.

[0091] Since the etching deviation determined in the traditional solution is not accurate, in this implementation, after the first mask pattern is determined, the first etching deviation corresponding to the first mask pattern is determined based on the etching model proposed above. Since the first etching deviation obtained based on the etching model is relatively accurate, the first target mask pattern that better meets the actual requirements can be determined.

[0092] In addition, in practical applications, because the OPC script, lithography compensation, and lithography model are responsible for generating all the mask data for the process layer corresponding to this technology node, and changing one part affects the whole, they cannot be easily modified. Therefore, during the actual process research and development and the improvement of the yield of specific chip products, the etching script is often adjusted. Therefore, in practice, when the etching script changes, the above etching model can be dynamically adjusted according to the collected wafer data.

[0093] A mask pattern determination method provided by an embodiment of the present application. The etching deviation is determined by the first etching pattern and the first lithography pattern, and the first etching image corresponding to the first etching pattern is obtained by fusing the first sub-image and the second sub-image. The first sub-image is generated by the physical effect simulation unit based on the first lithography pattern, and the second sub-image is generated by the neural network unit based on the first lithography pattern. Among them, the neural network unit can effectively improve the fitting ability of the etching model to data, thereby improving the accuracy of the etching model to obtain an accurate first etching deviation. At the same time, the physical effect simulation unit of the etching simulates the actual physical effects and can prevent the overfitting of the etching model.

[0094] As mentioned in the above embodiment, the first target mask pattern can be determined based on the first etching deviation and the first target etching pattern, and a specific determination method is provided. In practical applications, since the first lithography pattern input into the etching model when the first etching deviation is first determined is obtained based on a traditional method and has low accuracy, the accuracy of the obtained first etching deviation may not meet the requirements. Therefore, another feasible implementation is provided here. Figure 3 Fig. 11 shows a schematic diagram of the first process for designing the first target mask pattern provided by an embodiment of the present application.

[0095] As Figure 3 shown, S106 may include the following steps:

[0096] S1061: Compensate the first target etching pattern based on the first etching deviation to obtain the first target lithography pattern.

[0097] S1062: Perform optical proximity effect correction based on the first target lithography pattern to obtain the second mask pattern.

[0098] S1063: Determine whether the first etching deviation does not meet the first preset condition; if the first etching deviation does not meet the first preset condition, execute S1064; if the first etching deviation meets the first preset condition, execute S1065.

[0099] S1064: Update the first mask pattern to the second mask pattern; and return to S102.

[0100] S1065: Determine the finally obtained second mask pattern as the first target mask pattern.

[0101] This implementation further improves the accuracy of the determined first etching deviation, thereby ensuring that the first target mask pattern better meets the actual requirements. In this implementation, multiple iterations will be performed to update the first mask pattern to a more accurate second mask pattern. Based on the second mask pattern, a more accurate first etching deviation can be obtained. By cycling in this way, the accuracy of the second mask pattern can be continuously improved.

[0102] As an alternative implementation, the first preset condition can be that the difference between the corresponding two first etching deviations in two adjacent iterative processes is less than a threshold. The size of this threshold can be set according to requirements. When the difference between the first etching deviations corresponding to two adjacent iterative processes is not large, it indicates that the first etching deviation obtained at this time is accurate enough. Therefore, the iteration can be stopped, and the finally obtained second mask pattern can be determined as the first target mask pattern.

[0103] Here, a specific implementation for designing the first target mask pattern is provided. Figure 4 FIG. shows the second flow diagram of designing the first target mask pattern provided by an embodiment of the present application. As Figure 4 shown, first obtain the first target etching pattern 401. The etching deviation can be determined based on the traditional scheme and the first target etching pattern 401 can be compensated to obtain the first target lithography pattern 402. After OPC, a mask pattern is obtained. After lithography simulation, the first lithography pattern is obtained, and then it is input into the etching model 403 for etching simulation to obtain the first etching pattern. The first etching deviation is obtained based on the first lithography pattern and the first etching pattern.

[0104] Further, after obtaining the first etching deviation, the first target etching pattern 401 is compensated based on the first etching deviation to obtain a new first target lithography pattern 402. Repeat this process until the first etching deviation meets the first preset condition, and determine the finally obtained mask pattern as the first target mask pattern.

[0105] In the above embodiments, since the first photolithography pattern input into the etching model when the first etching deviation is first determined is obtained based on traditional methods and has low accuracy, the accuracy of the obtained first etching deviation may not meet the requirements. Therefore, in this implementation, through multiple iterations, the value of the first etching deviation is continuously calibrated to make the accuracy of the final first target mask pattern higher.

[0106] As mentioned above, when using the etching model provided in this application to determine the etching deviation, it is necessary to obtain the first mask pattern in advance. However, during the process from the first target etching pattern to the first mask pattern, it is necessary to obtain the etching deviation to compensate the first target etching pattern, and at this time, it cannot be achieved based on the etching model. Therefore, in this implementation, the method of establishing the first correspondence is used to determine the first etching deviation for the first time. As an optional implementation, based on the first target etching pattern, determining the first mask pattern may include:

[0107] Based on the first target etching pattern and the first correspondence, determining the corresponding second etching deviation;

[0108] Based on the second etching deviation, compensating the first target etching pattern to obtain the corresponding first target photolithography pattern;

[0109] Based on the first target photolithography pattern, performing optical proximity effect correction to obtain the first mask pattern.

[0110] In this embodiment, the first correspondence is the correspondence between the etching pattern and the etching deviation. As an optional implementation, the first correspondence can be implemented in the form of a table, and the correspondence between different pattern styles (including line width, pitch, etc.) and the etching deviation is saved based on the table. When it is necessary to determine the etching deviation, first match the pattern style corresponding to the first target etching pattern from the table, and then find the corresponding second etching deviation.

[0111] In addition, in practical applications, the first correspondence can also be corrected by the etching deviation obtained from the etching model to improve the accuracy.

[0112] In this implementation, first determine the second etching deviation through the first correspondence. Although the etching deviation obtained in this way has low accuracy, it can meet the basic requirements of accuracy, and the solution is simple and efficient.

[0113] In practical applications, the process from the target etching pattern to the etching pattern requires processes such as etching deviation compensation, OPC, and simulation, which takes a long time. Therefore, here an optional implementation is provided. After the fusion unit based on the etching model fuses at least one first sub-image and a second sub-image, the method may further include:

[0114] Obtain the first target etching pattern corresponding to the first mask pattern;

[0115] Construct a training sample based on the first target etching pattern and the first etching pattern;

[0116] Perform model training based on the training sample to obtain a lithography compensation and lithography etching model.

[0117] In this implementation manner, the lithography compensation and lithography etching model is used to complete processes such as OPC, lithography simulation, and etching simulation. The corresponding training data can be obtained through the etching model in the above text, that is, based on the etching model, the first etching pattern corresponding to the first mask pattern is obtained. Also, since the first mask pattern corresponds to the first target etching pattern. Therefore, a training sample can be constructed based on the correspondence between the first target etching pattern and the first etching pattern, and then model training is performed to obtain the lithography compensation and lithography etching model.

[0118] In this implementation manner, the lithography compensation and lithography etching model is directly trained to complete the process from the lithography pattern to the etching pattern. However, training the lithography compensation and lithography etching model requires a large amount of first etching pattern label data. In actual applications, the efficiency of obtaining label data through a scanning electron microscope is extremely low and cannot meet the requirements. Therefore, in this implementation manner, a large amount of training sample data is obtained through the etching model in the above text, and then the lithography compensation and lithography etching model is trained.

[0119] As mentioned in the above embodiments, in order to obtain the final target mask pattern, the value of the first etching deviation can be iteratively calibrated multiple times. However, each iteration requires processes such as etching deviation compensation, OPC, and simulation, which takes a long time and affects production efficiency. Therefore, a specific implementation manner is provided here. Figure 5 FIG. shows a first flow diagram of designing a second target mask pattern provided by an embodiment of the present application. As Figure 5 shown, after performing model training based on the training sample to obtain the lithography compensation and lithography etching model, the method may further include the following steps:

[0120] S501: Determine the second target lithography pattern based on the second target etching pattern.

[0121] S502: Input the second target lithography pattern into the lithography compensation and lithography etching model to obtain the second etching pattern, and input the second target lithography pattern into the pre-trained lithography compensation and lithography model to obtain the second lithography pattern.

[0122] In this implementation manner, the lithography compensation and lithography etching model is used to complete processes such as OPC, lithography simulation, and etching simulation. The lithography compensation and lithography model is used to implement steps such as OPC and lithography simulation.

[0123] Currently, when determining the second etched pattern from the second target lithography pattern, it is necessary to first perform OPC to obtain the corresponding mask pattern, and then perform lithography and etching simulations to obtain the second etched pattern. However, in this implementation, the second etched pattern can be directly obtained based on the second target lithography pattern through lithography compensation and the lithography-etching model.

[0124] Correspondingly, currently, when determining the second lithography pattern from the second target lithography pattern, it is necessary to first perform OPC to obtain the corresponding mask pattern, and then perform lithography simulation to obtain the second lithography pattern. However, in this implementation, the second lithography pattern can be directly obtained based on the second target lithography pattern through lithography compensation and the lithography model.

[0125] S503: Determine the third etching deviation based on the second etched pattern and the second lithography pattern.

[0126] S504: Compensate the second target etched pattern based on the third etching deviation to obtain the corrected second target lithography pattern.

[0127] S505: Determine whether the third etching deviation meets the second preset condition; if the third etching deviation does not meet the second preset condition, execute S506; if the third etching deviation meets the second preset condition, execute S507.

[0128] S506: Update the second target lithography pattern to the corrected second target lithography pattern; and return to S501.

[0129] S507: Determine the second target mask pattern based on the finally obtained corrected second target lithography pattern.

[0130] Corresponding to the first target etched pattern in the above text, in the design scenario of the mask pattern, the second target etched pattern in this implementation is the actually desired wafer pattern, and the second target lithography pattern can be obtained by compensating the etching deviation of the first target etched pattern.

[0131] As mentioned above, the pattern is usually interrupted, and each edge corresponds to a third etching deviation. Therefore, as an optional implementation, the above process can be sequentially executed for each edge separately.

[0132] As an optional implementation, the second preset condition can be that the difference between the corresponding two third etching deviations in two adjacent iterative processes is less than a threshold. The size of this threshold can be set according to requirements. When the difference between the third etching deviations corresponding to two adjacent iterative processes is not large, it indicates that the third etching deviation obtained at this time is accurate enough, so the iteration can be stopped.

[0133] When performing etch bias compensation for the first time, the etch bias can be determined through traditional solutions. However, since the accuracy of the etch bias determined by traditional solutions is low, in this implementation, the third etch bias is updated through multiple iterations of lithography compensation and lithography-etching models as well as lithography compensation and lithography models. Finally, a sufficiently accurate third etch bias is obtained, thereby obtaining an accurate second target lithography pattern. Furthermore, through OPC, the second target mask pattern required in practice can be obtained, and finally, the second target mask pattern is used as the mask pattern for the final design.

[0134] Here, a specific implementation for designing the second target mask pattern is provided. Figure 6 FIG. shows the second flow diagram of designing the second target mask pattern provided by an embodiment of the present application. As Figure 6 shown, first obtain the second target etch pattern 601. The etch bias can be determined based on traditional solutions first and the second target etch pattern 601 is compensated to obtain the second target lithography pattern 602. The second target lithography pattern 602 is respectively input into the lithography compensation and lithography-etching model 603 and the lithography compensation and lithography model 604, and the second lithography pattern and the second etch pattern are correspondingly obtained, and then the third etch bias is obtained.

[0135] Furthermore, after obtaining the third etch bias, the second target etch pattern 601 is compensated based on the third etch bias to obtain a new second target lithography pattern 602, and the above process is repeated until the third etch bias meets the second preset condition. Finally, based on the finally obtained second target lithography pattern 602, the second target mask pattern required in practice can be obtained through OPC.

[0136] In this implementation, through the lithography compensation and lithography-etching model established in the above embodiment and the pre-trained lithography compensation and lithography model, the process from the second target lithography pattern to the second etch pattern and the second lithography pattern is directly completed, thereby saving a large amount of time in the iteration and being able to quickly determine the second target mask pattern that meets the requirements, improving production efficiency.

[0137] As mentioned above, when performing etch bias compensation for the first time, the etch bias can be determined through traditional solutions. As an alternative implementation, based on the second target etch pattern, determining the second target lithography pattern may include:

[0138] Based on the second target etch pattern and the first correspondence, determine the corresponding fourth etch bias;

[0139] Based on the fourth etch bias, compensate the second target etch pattern to obtain the corresponding second target lithography pattern.

[0140] In this embodiment, the first correspondence is the correspondence between the etched pattern and the etching deviation. As an alternative implementation, the first correspondence can be implemented in the form of a table, which stores the correspondence between different pattern styles (including line width, spacing, etc.) and the etching deviation. When it is necessary to determine the etching deviation, first match the pattern style corresponding to the second target etched pattern in the table, and then find the corresponding fourth etching deviation.

[0141] In this implementation, the fourth etching deviation is first determined through the first correspondence. Although the accuracy of the etching deviation obtained by this method is low, it can meet the basic requirements of accuracy, and the solution is simple and the efficiency is high.

[0142] As mentioned in the above embodiment, the etching model provided by the present application includes a neural network unit and at least one physical effect simulation unit. Among them, the neural network unit needs to be trained to ensure that the etching model outputs accurate results. Therefore, an alternative implementation is provided here. Figure 7 The schematic diagram of the training process of the etching model provided by an embodiment of the present application is shown. As Figure 7 shown, before using the etching model, the method further includes the following steps:

[0143] S701: Obtain a photolithographic pattern sample and a corresponding etched image label.

[0144] S702: Input the photolithographic pattern sample into at least one physical effect simulation unit to correspondingly obtain at least one third sub-image, and input the photolithographic pattern sample into the initial neural network unit to obtain a fourth sub-image.

[0145] S703: Based on the fusion unit, fuse at least one third sub-image and the fourth sub-image to obtain a second etched image after etching the photolithographic pattern sample.

[0146] S704: Obtain the dimensional difference between the first graphic key dimension of the etched image label and the second graphic key dimension of the second etched image.

[0147] S705: Based on the dimensional difference, train the initial neural network unit to obtain a neural network unit.

[0148] S706: Determine the etching model according to the neural network unit, the physical effect simulation unit, and the fusion unit.

[0149] In this implementation, the photolithographic pattern sample corresponds to the etched image label, and the photolithographic pattern sample becomes the etched image label after etching. Therefore, by training the neural network unit with the photolithographic pattern sample and the corresponding etched image label, the etching model can output accurate results.

[0150] In this embodiment, the critical dimension of the first pattern refers to the critical dimension corresponding to the pattern in the etched image label, and the critical dimension of the second pattern refers to the critical dimension corresponding to the pattern in the second etched image, which can be calculated based on the corresponding pattern. The dimension difference is obtained by comparing the calculated critical dimension of the first pattern and the critical dimension of the second pattern, and then it is determined whether the model converges based on the evaluation function. In the case where the model does not converge, the parameters of the initial neural network unit can be adjusted iteratively multiple times, and finally the neural network unit that meets the requirements can be obtained. In addition, in practical applications, the combination of physical effect simulation units can also be adjusted through the above training method, so as to optimize and adjust the entire etching model.

[0151] In the process of determining whether the model converges based on the evaluation function, the evaluation can also be implemented for each side of the pattern. As an alternative implementation, evaluation points can be set on the sides to be evaluated, and then the positions of the evaluation points at the same position of the two patterns are compared, and the evaluation function value is determined based on the distance difference, so as to determine whether the output result of the model is accurate.

[0152] The above embodiment also mentions that in practice, the etching script often changes. When the etching script changes, the above etching model can be dynamically adjusted according to the collected wafer data. Since the model of the present application can be trained through actual data, a new etching model can be obtained quickly, thereby improving production efficiency.

[0153] Furthermore, automated continuous modeling can be realized. By continuously collecting SEM images in the actual production process, the etching model can be automatically updated after the process changes. For example, the wafer image after etching in actual production can be obtained through SEM, and then the pattern contour of each SEM image is extracted as the etched image label, and the corresponding lithography pattern is used as the lithography pattern sample for training the model.

[0154] This embodiment provides a training method for an etching model. The initial neural network unit is trained through the lithography pattern sample and the corresponding etched pattern label. In the case where there is a difference between the simulation image and the label image, the neural network unit is adjusted, so that the etching model can output a result that conforms to the actual situation.

[0155] Based on the mask pattern determination method provided in the above embodiment, correspondingly, the embodiment of the present application also provides a mask pattern determination device. Figure 8 The structural schematic diagram of the mask pattern determination device provided by the embodiment of the present application is shown. As Figure 8 shown, the device includes the following modules:

[0156] A determination module 801, configured to determine a first mask pattern based on a first target etched pattern;

[0157] An acquisition module 802, configured to acquire a first lithography pattern after lithography of the first mask pattern;

[0158] An input module 803, configured to input the first lithography pattern into at least one physical effect simulation unit of an etching model, correspondingly obtaining at least one first sub-image, and inputting the first lithography pattern into a neural network unit of the etching model to obtain a second sub-image; the neural network unit is trained based on a lithography pattern sample and a corresponding etching image label;

[0159] A fusion module 804, configured to fuse the at least one first sub-image and the second sub-image based on a fusion unit of the etching model to obtain a first etched pattern after etching the first lithography pattern;

[0160] A determination module 801 is further configured to determine a first etching deviation of the first lithography pattern based on the first etched pattern and the first lithography pattern;

[0161] The determination module 801 is further configured to determine a first target mask pattern based on the first etching deviation and the first target etched pattern.

[0162] The device provided in the embodiments of the present application is the same as the method in the above embodiments, so the two have the same embodiments and beneficial effects, which will not be elaborated here.

[0163] In some embodiments, the determination module 801 is specifically configured to:

[0164] Compensate the first target etched pattern based on the first etching deviation to obtain a first target lithography pattern;

[0165] Perform optical proximity effect correction based on the first target lithography pattern to obtain a second mask pattern;

[0166] Update the first mask pattern to the second mask pattern; and return to the step of acquiring the first lithography pattern after lithography of the first mask pattern until the first etching deviation meets a first preset condition;

[0167] Determine the finally obtained second mask pattern as the first target mask pattern.

[0168] In this implementation manner, through multiple iterations, the value of the first etching deviation is continuously calibrated, so that the accuracy of the final first target mask pattern is higher.

[0169] In some embodiments, the determination module 801 is specifically configured to:

[0170] Determine a corresponding second etching deviation based on the first target etched pattern and a first correspondence; the first correspondence is the correspondence between an etched pattern and an etching deviation;

[0171] Based on the second etching deviation, compensate the first target etching pattern to obtain the corresponding first target lithography pattern;

[0172] Perform optical proximity effect correction based on the first target lithography pattern to obtain the first mask pattern.

[0173] In this implementation, the second etching deviation is determined through the first correspondence first, and the solution is simple and efficient.

[0174] In some embodiments, the obtaining module 802 is further configured to obtain the first target etching pattern corresponding to the first mask pattern after fusing at least one first sub-image and a second sub-image by a fusion unit based on an etching model;

[0175] The mask pattern determination device further includes: an etching module, configured to construct a training sample according to the first target etching pattern and the first etching pattern;

[0176] A training module, configured to perform model training according to the training sample to obtain a lithography compensation and lithography etching model.

[0177] In this implementation, a large amount of training sample data is obtained through the etching model in the foregoing text, and then a relatively accurate lithography compensation and lithography etching model can be trained.

[0178] In some embodiments, the determination module 801 is further configured to determine a second target lithography pattern based on the second target etching pattern after performing model training according to the training sample to obtain a lithography compensation and lithography etching model;

[0179] The input module 803 is further configured to input the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etching pattern, and input the second target lithography pattern into a pre-trained lithography compensation and lithography model to obtain a second lithography pattern;

[0180] The determination module 801 is further configured to determine a third etching deviation based on the second etching pattern and the second lithography pattern;

[0181] The mask pattern determination device further includes: a compensation module, configured to compensate the second target etching pattern based on the third etching deviation to obtain a corrected second target lithography pattern;

[0182] An update module, configured to update the second target lithography pattern to the corrected second target lithography pattern; and return to the step of inputting the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etching pattern, and inputting the second target lithography pattern into a pre-trained lithography compensation and lithography model to obtain a second lithography pattern until the third etching deviation meets a second preset condition;

[0183] Based on the finally obtained corrected second target lithography pattern, determine the second target mask pattern.

[0184] This implementation saves a large amount of time in the iteration, can quickly determine the second target mask pattern that meets the requirements, and improves production efficiency.

[0185] In some embodiments, the determining module 801 is specifically configured to:

[0186] Based on the second target etching pattern and the first correspondence, determine the corresponding fourth etching deviation; the first correspondence is the correspondence between the etching pattern and the etching deviation;

[0187] Based on the fourth etching deviation, compensate the second target etching pattern to obtain the corresponding second target lithography pattern.

[0188] The solution for determining the etching deviation in this implementation is simple and has high efficiency.

[0189] In some embodiments, the obtaining module 802 is further configured to obtain a lithography pattern sample and a corresponding etching image label before inputting the first lithography pattern into at least one physical effect simulation unit of the etching model to correspondingly obtain at least one first sub-image, and inputting the first lithography pattern into the neural network unit of the etching model to obtain a second sub-image;

[0190] The input module 803 is further configured to input the lithography pattern sample into at least one physical effect simulation unit to correspondingly obtain at least one third sub-image, and input the lithography pattern sample into the initial neural network unit to obtain a fourth sub-image;

[0191] The fusion module 804 is further configured to fuse at least one third sub-image and the fourth sub-image based on the fusion unit to obtain a second etched image after etching the lithography pattern sample;

[0192] The obtaining module 802 is further configured to obtain the dimension difference between the first graphic key dimension of the etching image label and the second graphic key dimension of the second etched image;

[0193] The training module is further configured to train the initial neural network unit based on the dimension difference to obtain the neural network unit;

[0194] The determining module 801 is further configured to determine the etching model according to the neural network unit, the physical effect simulation unit, and the fusion unit.

[0195] This implementation trains the initial neural network unit through the lithography pattern sample and the corresponding etching pattern label, enabling the etching model to output accurate results that match the actual situation.

[0196] Figure 9 It shows a schematic diagram of the hardware structure of the mask pattern determination device provided by an embodiment of the present application. As Figure 9 shown, the mask pattern determination device may include a processor 901 and a memory 902 storing computer program instructions.

[0197] Specifically, the above-mentioned processor 901 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured as one or more integrated circuits for implementing the embodiments of the present application.

[0198] The memory 902 may include a mass storage for data or instructions. By way of example and not limitation, the memory 902 may include a Hard Disk Drive (HDD), a floppy disk drive, a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 902 may include a removable or non-removable (or fixed) medium. In a suitable case, the memory 902 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 902 is a non-volatile solid-state memory.

[0199] The memory 902 may include a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk storage media device, an optical storage media device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Thus, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present disclosure.

[0200] The processor 901 reads and executes the computer program instructions stored in the memory 902 to implement any one of the mask pattern determination methods in the above embodiments.

[0201] In an example, the mask pattern determination device may further include a communication interface 903 and a bus 904. The processor 901, the memory 902, and the communication interface 903 are connected through the bus 904 to complete mutual communication.

[0202] The communication interface 903 is mainly used to implement the communication between various modules, devices, units, and / or equipment in the embodiments of the present application.

[0203] The bus 904 includes hardware, software, or both, and couples the components of the mask pattern determination device to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. In a suitable case, the bus 904 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0204] In addition, in combination with the mask pattern determination method in the above embodiments, the embodiments of the present application can be implemented by providing a computer storage medium. Computer program instructions are stored on the computer storage medium; when the computer program instructions are executed by a processor, any one of the mask pattern determination methods in the above embodiments is implemented.

[0205] The embodiments of the present application also provide a computer program product, including a computer program, and when the computer program is executed by a processor, any one of the mask pattern determination methods in the above embodiments is implemented.

[0206] It should be clear that the present application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps after understanding the spirit of the present application.

[0207] The functional blocks shown in the above structural block diagrams can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an ASIC, appropriate firmware, a plug-in, a functional card, and so on. When implemented in software, the elements of the present application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium or transmitted via a data signal carried in a carrier wave on a transmission medium or a communication link. A "machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical discs, hard disks, fiber optic media, radio frequency (RF) links, and so on. The code segment can be downloaded via a computer network such as the Internet, an intranet, and so on.

[0208] It should also be noted that the exemplary embodiments mentioned in the present application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps can be executed in the order mentioned in the embodiments, or different from the order in the embodiments, or several steps can be executed simultaneously.

[0209] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of a method, apparatus, medium, and product for determining a mask pattern according to an embodiment of the present disclosure. It should be understood that each block in the flowchart and / or block diagram, and the combination of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the functions / operations specified in one or more blocks of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It should also be understood that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can also be implemented by dedicated hardware that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0210] The above content is only the specific implementation manner of the present application. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, modules, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again. It should be understood that the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application.

Claims

1. A method for determining a mask pattern, characterized in that, Including: Determine a first mask pattern based on a first target etching pattern; Obtain a first lithography pattern after lithography of the first mask pattern; Input the first lithography pattern into at least one physical effect simulation unit of an etching model to correspondingly obtain at least one first sub-image, and input the first lithography pattern into a neural network unit of the etching model to obtain a second sub-image; the neural network unit is trained based on lithography pattern samples and corresponding etching image labels; Fuse the at least one first sub-image and the second sub-image based on a fusion unit of the etching model to obtain a first etched pattern after etching the first lithography pattern; Determine a first etching deviation of the first lithography pattern based on the first etched pattern and the first lithography pattern; Determine a first target mask pattern based on the first etching deviation and the first target etching pattern.

2. The mask pattern determination method according to claim 1, characterized in that The determining the first target mask pattern based on the first etching deviation and the first target etching pattern includes: Compensate the first target etching pattern based on the first etching deviation to obtain a first target lithography pattern; Perform optical proximity effect correction on the first target lithography pattern to obtain a second mask pattern; In the case where the first etching deviation does not meet a first preset condition, update the first mask pattern to the second mask pattern; and return to the step of obtaining the first lithography pattern after lithography of the first mask pattern until the first etching deviation meets the first preset condition; In the case where the first etching deviation meets the first preset condition, determine the current second mask pattern as the first target mask pattern.

3. The mask pattern determination method according to claim 1, characterized in that The determining the first mask pattern based on the first target etching pattern includes: Determine a corresponding second etching deviation based on the first target etching pattern and a first correspondence; the first correspondence is a correspondence between an etching pattern and an etching deviation; Compensate the first target etching pattern based on the second etching deviation to obtain the corresponding first target lithography pattern; Perform optical proximity effect correction on the first target lithography pattern to obtain the first mask pattern.

4. The mask pattern determination method according to claim 1, wherein After the fusion unit of the etching model fuses the at least one first sub-image and the second sub-image, the method further includes: Obtain a first target etching pattern corresponding to the first mask pattern; Construct a training sample according to the first target etching pattern and the first etched pattern; Perform model training according to the training sample to obtain a lithography compensation and lithography etching model.

5. The mask pattern determination method according to claim 4, characterized in that After the performing model training according to the training sample to obtain a lithography compensation and lithography etching model, the method further includes: Determine a second target lithography pattern based on a second target etching pattern; Input the second target lithography pattern into the lithography compensation and lithography etching model to obtain a second etched pattern, and input the second target lithography pattern into a pre-trained lithography compensation and lithography model to obtain a second lithography pattern; Determine a third etching deviation based on the second etched pattern and the second lithographed pattern; In the case where the third etching deviation does not meet the second preset condition, compensate the second target etched pattern based on the third etching deviation to obtain a corrected second target lithographed pattern; Update the second target lithographed pattern to the corrected second target lithographed pattern; and return to the steps of inputting the second target lithographed pattern into the lithography compensation and lithography etching model to obtain a second etched pattern, and inputting the second target lithographed pattern into a pre-trained lithography compensation and lithography model to obtain a second lithographed pattern until the third etching deviation meets the second preset condition; In the case where the third etching deviation meets the second preset condition, determine a second target mask pattern based on the current corrected second target lithographed pattern.

6. The method for determining a mask pattern according to claim 5, wherein The determining the second target lithographed pattern based on the second target etched pattern includes: Determine a corresponding fourth etching deviation based on the second target etched pattern and a first correspondence relationship; the first correspondence relationship is the correspondence relationship between the etched pattern and the etching deviation; Compensate the second target etched pattern based on the fourth etching deviation to obtain the corresponding second target lithographed pattern.

7. The method for determining a mask pattern according to any one of claims 1 to 6, characterized in that, Before inputting the first lithographed pattern into at least one physical effect simulation unit of the etching model to correspondingly obtain at least one first sub-image, and inputting the first lithographed pattern into the neural network unit of the etching model to obtain a second sub-image, the method further includes: Obtain the lithographed pattern sample and the corresponding etched image label; Input the lithographed pattern sample into the at least one physical effect simulation unit to correspondingly obtain at least one third sub-image, and input the lithographed pattern sample into an initial neural network unit to obtain a fourth sub-image; Fuse the at least one third sub-image and the fourth sub-image based on the fusion unit to obtain a second etched image after etching the lithographed pattern sample; Obtain the dimension difference between the first graphic key dimension of the etched image label and the second graphic key dimension of the second etched image; Train the initial neural network unit based on the dimension difference to obtain the neural network unit; Determine the etching model according to the neural network unit, the physical effect simulation unit, and the fusion unit.

8. A mask pattern determination device, characterized in that, including: A processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the mask pattern determination method according to any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium, characterized in that, Computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by the processor, the mask pattern determination method according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device is caused to execute the mask pattern determination method according to any one of claims 1 to 7.

Images